# OpenAI — Deliberative alignment: reasoning enables safer language models

- Company: OpenAI (openai.com)
- Announced: 2024-12-20T10:00:00+00:00
- Category: safety-policy-update
- Subject: GPT / ChatGPT / API
- Models affected: o1 models
- Source: https://openai.com/index/deliberative-alignment
- Record: https://forck.live/items/656-deliberative-alignment-reasoning-enables-safer-language-models

OpenAI introduces a new alignment strategy called deliberative alignment for o1 models, which teaches safety specifications and reasoning over them.

## Evidence

Verbatim from https://openai.com/index/deliberative-alignment:

> Introducing our new alignment strategy for o1 models, which are directly taught safety specifications and how to reason over them.

---

Record: https://forck.live/items/656-deliberative-alignment-reasoning-enables-safer-language-models
Catalogue: https://forck.live/llms.txt
Feed: https://forck.live/feed.md